Table 1 Summary of all computed texture analysis categories with corresponding features.

From: Prognostic value of texture analysis from cardiac magnetic resonance imaging in patients with Takotsubo syndrome: a machine learning based proof-of-principle approach

Texture category

Texture feature

Histogram

Mean, variance, skewness, kurtosis

Grey-level co-occurrence matrix (GLCM)

(computed for four directions [(a,0), (0,a), (a,a), (0,-a)] at five interpixel distances a = 1–5; 6 bits/pixel)

Angular second moment, contrast, correlation, entropy, sum entropy, sum of squares, sum average, sum variance, inverse different moment, difference entropy, difference variance

Run-length matrix (RLM)

(computed for four angles [vertical, horizontal, 0°, and 135°]; 6 bits/pixel)

Run-length non-uniformity, grey-level non-uniformity, long run emphasis, short run emphasis, fraction of image in runs

Absolute gradient

(4 bits/pixel)

Gradient mean, variance, skewness, kurtosis, and non-zeros

Autoregressive model

Teta 1–4, sigma

Wavelet transform

(calculated for seven subsampling factors n = 1–7)

Energy of wavelet coefficients in low-frequency sub-bands, horizontal high-frequency sub-bands, vertical high-frequency sub-bands, diagonal high-frequency sub-bands

Back to article page